This role is for one of the Weekday's clients

Salary range: Rs 2000000 - Rs 6000000 (ie INR 20-60 LPA)

Min Experience: 3 years

JobType: full-time

We are seeking a skilled and motivated AI Engineer with hands-on experience in Retrieval-Augmented Generation (RAG) to join our growing team. In this role, you will design, build, and optimize AI systems that leverage both large language models (LLMs) and structured/unstructured knowledge bases to deliver intelligent and contextually accurate responses. You will be at the forefront of applied AI, working on cutting-edge solutions that bridge the gap between traditional NLP pipelines and next-generation generative AI models.

Requirements

Key Responsibilities:

• Design and develop RAG-based architectures integrating vector databases, document retrieval systems, and LLMs.
• Implement end-to-end pipelines that perform document ingestion, chunking, embedding generation, indexing, and retrieval.
• Fine-tune and optimize retrieval mechanisms using tools such as FAISS, Weaviate, Pinecone, or Elasticsearch.
• Integrate APIs of foundation models like OpenAI, Cohere, or Hugging Face models with retrieval systems to produce context-rich outputs.
• Work with cross-functional teams including ML engineers, data scientists, and product teams to deliver AI-powered features.
• Evaluate model performance using both qualitative and quantitative metrics and iteratively refine system behavior.
• Ensure the accuracy, relevance, and safety of model-generated responses by fine-tuning prompts and optimizing knowledge grounding.
• Stay updated with the latest research in generative AI, RAG systems, and prompt engineering.

Required Skills and Qualifications:

• 3 to 9 years of experience in AI/ML/NLP with a strong focus on building and deploying generative AI models.
• Deep understanding of Retrieval-Augmented Generation (RAG) concepts and architecture.
• Proficiency with vector databases (e.g., FAISS, Pinecone, Weaviate, Vespa) and embedding generation (e.g., SentenceTransformers, OpenAI Embeddings).
• Strong programming skills in Python and experience with libraries such as LangChain, Transformers, Hugging Face, PyTorch, or TensorFlow.
• Familiarity with LLM APIs like OpenAI (GPT-3.5/4), Anthropic, Cohere, or similar.
• Experience working with unstructured data sources (e.g., PDFs, HTML, text files) and knowledge of chunking and context window optimization.
• Ability to design scalable pipelines for real-time or batch inference using cloud platforms (AWS, Azure, GCP).
• Excellent problem-solving, debugging, and analytical skills.
• Strong written and verbal communication skills with the ability to explain technical concepts to non-technical stakeholders.

Good to Have:

• Experience with LangChain, LlamaIndex, or other retrieval frameworks.
• Exposure to knowledge graphs, search ranking algorithms, and hybrid retrieval methods.
• Familiarity with prompt engineering and few-shot learning strategies.
• Contributions to open-source AI projects or published research in the field of generative AI.